Merge tag 'seccomp-v5.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull seccomp updates from Kees Cook:

 - Add "atomic addfd + send reply" mode to SECCOMP_USER_NOTIF to better
   handle EINTR races visible to seccomp monitors. (Rodrigo Campos,
   Sargun Dhillon)

 - Improve seccomp selftests for readability in CI systems. (Kees Cook)

* tag 'seccomp-v5.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  selftests/seccomp: Avoid using "sysctl" for report
  selftests/seccomp: Flush benchmark output
  selftests/seccomp: More closely track fds being assigned
  selftests/seccomp: Add test for atomic addfd+send
  seccomp: Support atomic "addfd + send reply"

1 files changed, 45 insertions, 6 deletions

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 9f58049ac16d..057e17f3215d 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -107,6 +107,7 @@ struct seccomp_knotif {
  *      installing process should allocate the fd as normal.
  * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC
  *         is allowed.
+ * @ioctl_flags: The flags used for the seccomp_addfd ioctl.
  * @ret: The return value of the installing process. It is set to the fd num
  *       upon success (>= 0).
  * @completion: Indicates that the installing process has completed fd
@@ -118,6 +119,7 @@ struct seccomp_kaddfd {
 	struct file *file;
 	int fd;
 	unsigned int flags;
+	__u32 ioctl_flags;
 
 	union {
 		bool setfd;
@@ -1065,18 +1067,37 @@ static u64 seccomp_next_notify_id(struct seccomp_filter *filter)
 	return filter->notif->next_id++;
 }
 
-static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd)
+static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_knotif *n)
 {
+	int fd;
+
 	/*
 	 * Remove the notification, and reset the list pointers, indicating
 	 * that it has been handled.
 	 */
 	list_del_init(&addfd->list);
 	if (!addfd->setfd)
-		addfd->ret = receive_fd(addfd->file, addfd->flags);
+		fd = receive_fd(addfd->file, addfd->flags);
 	else
-		addfd->ret = receive_fd_replace(addfd->fd, addfd->file,
-						addfd->flags);
+		fd = receive_fd_replace(addfd->fd, addfd->file, addfd->flags);
+	addfd->ret = fd;
+
+	if (addfd->ioctl_flags & SECCOMP_ADDFD_FLAG_SEND) {
+		/* If we fail reset and return an error to the notifier */
+		if (fd < 0) {
+			n->state = SECCOMP_NOTIFY_SENT;
+		} else {
+			/* Return the FD we just added */
+			n->flags = 0;
+			n->error = 0;
+			n->val = fd;
+		}
+	}
+
+	/*
+	 * Mark the notification as completed. From this point, addfd mem
+	 * might be invalidated and we can't safely read it anymore.
+	 */
 	complete(&addfd->completion);
 }
 
@@ -1120,7 +1141,7 @@ static int seccomp_do_user_notification(int this_syscall,
 						 struct seccomp_kaddfd, list);
 		/* Check if we were woken up by a addfd message */
 		if (addfd)
-			seccomp_handle_addfd(addfd);
+			seccomp_handle_addfd(addfd, &n);
 
 	}  while (n.state != SECCOMP_NOTIFY_REPLIED);
 
@@ -1581,7 +1602,7 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
 	if (addfd.newfd_flags & ~O_CLOEXEC)
 		return -EINVAL;
 
-	if (addfd.flags & ~SECCOMP_ADDFD_FLAG_SETFD)
+	if (addfd.flags & ~(SECCOMP_ADDFD_FLAG_SETFD | SECCOMP_ADDFD_FLAG_SEND))
 		return -EINVAL;
 
 	if (addfd.newfd && !(addfd.flags & SECCOMP_ADDFD_FLAG_SETFD))
@@ -1591,6 +1612,7 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
 	if (!kaddfd.file)
 		return -EBADF;
 
+	kaddfd.ioctl_flags = addfd.flags;
 	kaddfd.flags = addfd.newfd_flags;
 	kaddfd.setfd = addfd.flags & SECCOMP_ADDFD_FLAG_SETFD;
 	kaddfd.fd = addfd.newfd;
@@ -1616,6 +1638,23 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
 		goto out_unlock;
 	}
 
+	if (addfd.flags & SECCOMP_ADDFD_FLAG_SEND) {
+		/*
+		 * Disallow queuing an atomic addfd + send reply while there are
+		 * some addfd requests still to process.
+		 *
+		 * There is no clear reason to support it and allows us to keep
+		 * the loop on the other side straight-forward.
+		 */
+		if (!list_empty(&knotif->addfd)) {
+			ret = -EBUSY;
+			goto out_unlock;
+		}
+
+		/* Allow exactly only one reply */
+		knotif->state = SECCOMP_NOTIFY_REPLIED;
+	}
+
 	list_add(&kaddfd.list, &knotif->addfd);
 	complete(&knotif->ready);
 	mutex_unlock(&filter->notify_lock);